Spoiler Alert: Narrative Forecasting as a Metric for Tension in LLM Storytelling
Peiqi Sui · Yutong Zhu · Tianyi Cheng · Peter West · Richard Jean So · Hoyt Long · Ari Holtzman
We introduce the 100-Ending metric to evaluate the narrative tension of LLM stories through ending predictability, and use it to design an LLM storytelling system that demonstrates form-level constraints are key to compelling AI fiction.
摘要
LLMs have so far failed both to generate consistently compelling stories and to recognize this failure—on the leading creative-writing benchmark (EQ-Bench), LLM judges rank zero-shot AI stories above *New Yorker* short stories, a gold standard for literary fiction. We argue that existing rubrics overlook a key dimension of compelling human stories: narrative tension. We introduce the *100-Endings* metric, which walks through a story sentence by sentence: at each position, a model predicts how the story will end 100 times given only the text so far, and we measure tension as how often predictions fail to match the ground truth. Beyond the mismatch rate, the sentence-level curve also yields complementary statistics that track plot-level twists and revelations, such as the *inflection rate*, a geometric measure of how frequently the curve reverses direction. Unlike rubric-based judges, *100-Endings* correctly ranks *New Yorker* stories far above LLM outputs. Grounded in narratological principles, we design a story-generation pipeline using structural constraints, including analysis of story templates, idea formulation, and narrative scaffolding. Our pipeline significantly increases narrative tension as measured by the *100-Endings* metric, while maintaining performance on the EQ-Bench leaderboard.